llama.cpp
ggml-cuda: Adding support for unified memory
#8035
Merged

ggml-cuda: Adding support for unified memory #8035

JohannesGaessler merged 7 commits into ggml-org:master from master
matteoserva
JohannesGaessler
JohannesGaessler
matteoserva
Nexesenex
matteoserva
Nexesenex
mofosyne mofosyne added Review Complexity : Low
JohannesGaessler
JohannesGaessler
JohannesGaessler
matteoserva
JohannesGaessler
matteoserva
JohannesGaessler
matteoserva
slaren
matteoserva
slaren
slaren
matteoserva
github-actions github-actions added documentation
Gingeropolous
matteoserva
matteoserva Adding support for unified memory
5577cada
matteoserva adding again the documentation about unified memory
82fadbd7
matteoserva refactoring: Moved the unified memory code in the correct location.
f258b927
matteoserva Fixed compilation error when using hipblas
c1d255e9
JohannesGaessler
JohannesGaessler commented on 2024-07-31
matteoserva cleaning up the documentation
390f54eb
matteoserva
JohannesGaessler
JohannesGaessler commented on 2024-07-31
matteoserva Updating the documentation
7444bad4
matteoserva adding one more case where the PR should not be enabled
f38c6f3c
JohannesGaessler
JohannesGaessler approved these changes on 2024-07-31
JohannesGaessler JohannesGaessler merged afbb4c13 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone